#41 · Primary category： LLM Application Frameworks
rig
⚙️🦀 Build modular and scalable LLM Applications in Rust
Project last updated：08/30/26
GitHub Stars
8.4K
Forks
942
Contributors
230
License
MIT
Why we included this project
Rig is a Rust library for building LLM applications, aimed at teams that want to stay in Rust rather than wiring together separate crates. It gives you a single API across more than 20 model providers and a range of vector stores, so you don't have to write the integration plumbing yourself. The agent runtime is the main draw, with support for multi-turn streaming, prompts, and tool calls, and the crate is designed so you can enable only the parts you need via feature flags. It also uses OpenTelemetry's GenAI conventions, which is nice if you already monitor your services and want consistent LLM telemetry. The project moves fast and the maintainers warn about breaking changes.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform